Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2411 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 6.3007. Min Range: -6.3007

Max Act: 6.3007. Min Act: -0.1700

Data Index: 6340366 (Open Web Text)

Max Activating Token Index: 917

Text #1

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.8750. Min Act: -0.1700

Data Index: 7395511 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.8861. Min Act: -0.1700

Data Index: 1040566 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.8567. Min Act: -0.1700

Data Index: 8307641 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7725. Min Act: -0.1700

Data Index: 8612767 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7834. Min Act: -0.1700

Data Index: 5961655 (Open Web Text)

Max Activating Token Index: 650

Text #6

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7280. Min Act: -0.1700

Data Index: 3912777 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7046. Min Act: -0.1700

Data Index: 6391388 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6887. Min Act: -0.1700

Data Index: 2994674 (Open Web Text)

Max Activating Token Index: 899

Text #9

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6924. Min Act: -0.1700

Data Index: 6888424 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6975. Min Act: -0.1700

Data Index: 6642387 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6910. Min Act: -0.1700

Data Index: 1064143 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7126. Min Act: -0.1700

Data Index: 2526047 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6502. Min Act: -0.1700

Data Index: 5452720 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.7045. Min Act: -0.1700

Data Index: 8320032 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6462. Min Act: -0.1700

Data Index: 1105741 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6316. Min Act: -0.1700

Data Index: 4714619 (Open Web Text)

Max Activating Token Index: 861

Text #17

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6646. Min Act: -0.1700

Data Index: 7601204 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6586. Min Act: -0.1700

Data Index: 6148133 (Open Web Text)

Max Activating Token Index: 989

Text #19

Max Range: 6.3007. Min Range: -6.3007

Max Act: 5.6294. Min Act: -0.1700

Data Index: 2854123 (Open Web Text)

Max Activating Token Index: 491